This PR adds Gujarati Language class along with (#5355)

* This PR adds Gujarati Language class along with
- stop words

* Add test for gu tokenizer

.github/contributors/punitvara.md

@@ -0,0 +1,107 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI UG (haftungsbeschränkt)](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your 
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [x] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect to my
+    contributions.
+
+    * [ ] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry                    |
+|------------------------------- | ------------------------ |
+| Name                           | Punit Vara	            |
+| Company name (if applicable)   |                          |
+| Title or role (if applicable)  | 		            |
+| Date                           | 2020-04-26               |
+| GitHub username                | punitvara                |
+| Website (optional)             | https://punitvara.com    |
+

spacy/lang/gu/__init__.py

@@ -0,0 +1,18 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from .stop_words import STOP_WORDS
+
+from ...language import Language
+
+
+class GujaratiDefaults(Language.Defaults):
+    stop_words = STOP_WORDS
+
+
+class Gujarati(Language):
+    lang = "gu"
+    Defaults = GujaratiDefaults
+
+
+__all__ = ["Gujarati"]

spacy/lang/gu/examples.py

@@ -0,0 +1,22 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.gu.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+
+sentences = [
+    "લોકશાહી એ સરકારનું એક એવું તંત્ર છે જ્યાં નાગરિકો મત દ્વારા સત્તાનો ઉપયોગ કરે છે.",
+    "તે ગુજરાત રાજ્યના ધરમપુર શહેરમાં આવેલું હતું",
+    "કર્ણદેવ પહેલો સોલંકી વંશનો રાજા હતો",
+    "તેજપાળને બે પત્ની હતી",
+    "ગુજરાતમાં ભારતીય જનતા પક્ષનો ઉદય આ સમયગાળા દરમિયાન થયો",
+    "આંદોલનકારીઓએ ચીમનભાઇ પટેલના રાજીનામાની માંગણી કરી.",
+    "અહિયાં શું જોડાય છે?",
+    "મંદિરનો પૂર્વાભિમુખ ભાગ નાના મંડપ સાથે થોડો લંબચોરસ આકારનો છે.",
+]

spacy/lang/gu/stop_words.py

@@ -0,0 +1,91 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+STOP_WORDS = set(
+    """
+એમ 
+આ
+એ
+રહી
+છે
+છો
+હતા
+હતું
+હતી
+હોય
+હતો
+શકે
+તે
+તેના
+તેનું
+તેને
+તેની
+તેઓ
+તેમને
+તેમના
+તેમણે
+તેમનું 
+તેમાં
+અને
+અહીં
+થી
+થઈ
+થાય
+જે
+ ને
+કે 
+ના
+ની
+નો
+ને
+નું 
+શું
+માં
+પણ
+પર
+જેવા
+જેવું
+જાય
+જેમ
+જેથી
+માત્ર
+માટે
+પરથી
+આવ્યું
+એવી
+આવી
+રીતે
+સુધી
+થાય
+થઈ
+સાથે
+લાગે
+હોવા
+છતાં
+રહેલા
+કરી
+કરે
+કેટલા
+કોઈ
+કેમ
+કર્યો
+કર્યુ 
+કરે
+સૌથી
+ત્યારબાદ 
+તથા
+દ્વારા 
+જુઓ
+જાઓ
+જ્યારે
+ત્યારે
+શકો
+નથી
+હવે
+અથવા
+થતો
+દર
+એટલો
+પરંતુ
+""".split()
+)

spacy/tests/conftest.py

@@ -103,6 +103,10 @@ def ga_tokenizer():
     return get_lang_class("ga").Defaults.create_tokenizer()
 
 
+@pytest.fixture(scope="session")
+def gu_tokenizer():
+    return get_lang_class("gu").Defaults.create_tokenizer()
+
 @pytest.fixture(scope="session")
 def he_tokenizer():
     return get_lang_class("he").Defaults.create_tokenizer()

spacy/tests/lang/gu/test_text.py

@@ -0,0 +1,20 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import pytest
+
+def test_gu_tokenizer_handlers_long_text(gu_tokenizer):
+    text = """પશ્ચિમ ભારતમાં આવેલું ગુજરાત રાજ્ય જે વ્યક્તિઓની માતૃભૂમિ છે"""
+    tokens = gu_tokenizer(text)
+    assert len(tokens) == 9
+
+@pytest.mark.parametrize(
+    "text,length",
+    [
+        ("ગુજરાતીઓ ખાવાના શોખીન માનવામાં આવે છે", 6),
+        ("ખેતરની ખેડ કરવામાં આવે છે.", 5),
+    ],
+)
+def test_gu_tokenizer_handles_cnts(gu_tokenizer, text, length):
+    tokens = gu_tokenizer(text)
+    assert len(tokens) == length